[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Condor-users] Guiding machine choices for the parallel universe
- Date: Sat, 6 Dec 2008 22:14:54 +0000
- From: "Alan Woodland" <alan.woodland@xxxxxxxxx>
- Subject: Re: [Condor-users] Guiding machine choices for the parallel universe
>> Fourthly how could free_nodes_in_my_subpool be implemented?
>> Or generally is there a nicer way to solve this without topological
>> changes to the network or intervention from each user of the parallel
> There's also the ParallelSchedulingGroups feature which may help.
That sounds like what I'm looking for, except I wanted a way to still
automatically fall back on cross-group allocations if either a) too
many machines were requested or b) too many machines were currently
busy in any one group. My reading of that was such that this would
never happen automatically. (I.e. WantParallelSchedulingGroup = true
is a boolean, not a fuzzy optimisation). Any suggestions?